SEQ CUB200

Classes

class datasets.seq_cub200.CUB200(root, train=True, transform=None, target_transform=None, download=False)

Bases: MyCUB200

Base CUB200 dataset.

class datasets.seq_cub200.MyCUB200(root, train=True, transform=None, target_transform=None, download=True)

Bases: Dataset

Overrides dataset to change the getitem function.

IMG_SIZE = 224

N_CLASSES = 200

class datasets.seq_cub200.SequentialCUB200(args)

Bases: ContinualDataset

Sequential CUB200 Dataset.

Parameters:

• NAME (str) – name of the dataset.

• SETTING (str) – setting of the dataset.

• N_CLASSES_PER_TASK (int) – number of classes per task.

• N_TASKS (int) – number of tasks.

• SIZE (tuple) – size of the images.

• MEAN (tuple) – mean of the dataset.

• STD (tuple) – standard deviation of the dataset.

• TRANSFORM (torchvision.transforms) – transformation to apply to the data.

• TEST_TRANSFORM (torchvision.transforms) – transformation to apply to the test data.

MEAN = [0.485, 0.456, 0.406]

NAME: str = 'seq-cub200'

N_CLASSES_PER_TASK: int = 20

N_TASKS: int = 10

SETTING: str = 'class-il'

SIZE: Tuple[int] = (224, 224)

STD = [0.229, 0.224, 0.225]

TEST_TRANSFORM = Compose(     Resize(size=256, interpolation=bicubic, max_size=None, antialias=True)     CenterCrop(size=(224, 224))     ToTensor()     Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) )

TRANSFORM = Compose(     Resize(size=(300, 300), interpolation=bicubic, max_size=None, antialias=True)     RandomCrop(size=(224, 224), padding=None)     RandomHorizontalFlip(p=0.5)     ToTensor()     Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) )

get_backbone()

get_batch_size()

get_class_names()

get_data_loaders()

Return type:

Tuple[DataLoader, DataLoader]

static get_denormalization_transform()

get_epochs()

static get_loss()

static get_normalization_transform()

static get_transform()